ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-8043] [MLLIB] [DOC] update NaiveBayes and SVM examples in doc

Browse source 
jira: https://issues.apache.org/jira/browse/SPARK-8043

I found some issues during testing the save/load examples in markdown Documents, as a part of 1.4 QA plan

Author: Yuhao Yang <hhbyyh@gmail.com>

Closes #6584 from hhbyyh/naiveDocExample and squashes the following commits:

a01a206 [Yuhao Yang] fix for Gaussian mixture
2fb8b96 [Yuhao Yang] update NaiveBayes and SVM examples in doc
This commit is contained in:
Yuhao Yang 2015-06-02 23:15:38 -07:00 committed by Xiangrui Meng
parent ccaa823290
commit 43adbd5611
3 changed files with 14 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
docs/mllib-clustering.md
View file

@ -249,11 +249,11 @@ public class GaussianMixtureExample {
GaussianMixtureModel gmm = new GaussianMixture().setK(2).run(parsedData.rdd());
// Save and load GaussianMixtureModel
gmm.save(sc, "myGMMModel")
GaussianMixtureModel sameModel = GaussianMixtureModel.load(sc, "myGMMModel")
gmm.save(sc.sc(), "myGMMModel");
GaussianMixtureModel sameModel = GaussianMixtureModel.load(sc.sc(), "myGMMModel");
// Output the parameters of the mixture model
for(int j=0; j<gmm.k(); j++) {
System.out.println("weight=%f\nmu=%s\nsigma=\n%s\n",
System.out.printf("weight=%f\nmu=%s\nsigma=\n%s\n",
gmm.weights()[j], gmm.gaussians()[j].mu(), gmm.gaussians()[j].sigma());
}
}

24
docs/mllib-linear-methods.md
View file

@ -163,11 +163,8 @@ object, and make predictions with the resulting model to compute the training
error.
{% highlight scala %}
import org.apache.spark.SparkContext
import org.apache.spark.mllib.classification.{SVMModel, SVMWithSGD}
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.util.MLUtils
// Load training data in LIBSVM format.
@ -231,15 +228,13 @@ calling `.rdd()` on your `JavaRDD` object. A self-contained application example
that is equivalent to the provided example in Scala is given bellow:
{% highlight java %}
import java.util.Random;
import scala.Tuple2;
import org.apache.spark.api.java.*;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.mllib.classification.*;
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.mllib.util.MLUtils;
import org.apache.spark.SparkConf;
@ -282,8 +277,8 @@ public class SVMClassifier {
System.out.println("Area under ROC = " + auROC);
// Save and load model
model.save(sc.sc(), "myModelPath");
SVMModel sameModel = SVMModel.load(sc.sc(), "myModelPath");
model.save(sc, "myModelPath");
SVMModel sameModel = SVMModel.load(sc, "myModelPath");
}
}
{% endhighlight %}
@ -315,15 +310,12 @@ a dependency.
</div>
<div data-lang="python" markdown="1">
The following example shows how to load a sample dataset, build Logistic Regression model,
The following example shows how to load a sample dataset, build SVM model,
and make predictions with the resulting model to compute the training error.
Note that the Python API does not yet support model save/load but will in the future.
{% highlight python %}
from pyspark.mllib.classification import LogisticRegressionWithSGD
from pyspark.mllib.classification import SVMWithSGD, SVMModel
from pyspark.mllib.regression import LabeledPoint
from numpy import array
# Load and parse the data
def parsePoint(line):
@ -334,12 +326,16 @@ data = sc.textFile("data/mllib/sample_svm_data.txt")
parsedData = data.map(parsePoint)
# Build the model
model = LogisticRegressionWithSGD.train(parsedData)
model = SVMWithSGD.train(parsedData, iterations=100)
# Evaluating the model on training data
labelsAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features)))
trainErr = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(parsedData.count())
print("Training Error = " + str(trainErr))
# Save and load model
model.save(sc, "myModelPath")
sameModel = SVMModel.load(sc, "myModelPath")
{% endhighlight %}
</div>
</div>

2
docs/mllib-naive-bayes.md
View file

@ -53,7 +53,7 @@ val splits = parsedData.randomSplit(Array(0.6, 0.4), seed = 11L)
val training = splits(0)
val test = splits(1)
val model = NaiveBayes.train(training, lambda = 1.0, model = "multinomial")
val model = NaiveBayes.train(training, lambda = 1.0, modelType = "multinomial")
val predictionAndLabel = test.map(p => (model.predict(p.features), p.label))
val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()